检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

6,098 篇 会议
904 篇 期刊文献
73 册 图书

馆藏范围

7,075 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,460 篇 工学
- 3,490 篇 计算机科学与技术...
- 2,915 篇 软件工程
- 1,334 篇 信息与通信工程
- 682 篇 控制科学与工程
- 478 篇 生物工程
- 443 篇 电气工程
- 438 篇 电子科学与技术（可...
- 332 篇 生物医学工程（可授...
- 309 篇 光学工程
- 272 篇 机械工程
- 234 篇 仪器科学与技术
- 214 篇 动力工程及工程热...
- 170 篇 化学工程与技术
- 161 篇 安全科学与工程
- 160 篇 交通运输工程
- 131 篇 建筑学
2,127 篇 理学
- 1,198 篇 数学
- 539 篇 物理学
- 496 篇 生物学
- 382 篇 统计学（可授理学、...
- 241 篇 系统科学
- 165 篇 化学
1,173 篇 管理学
- 705 篇 管理科学与工程(可...
- 519 篇 图书情报与档案管...
- 357 篇 工商管理
299 篇 医学
- 257 篇 临床医学
- 235 篇 基础医学(可授医学...
- 146 篇 公共卫生与预防医...
- 141 篇 药学(可授医学、理...
202 篇 法学
- 151 篇 社会学
145 篇 农学
119 篇 教育学
109 篇 经济学
27 篇 文学
16 篇 军事学
9 篇 艺术学
1 篇 哲学

主题

201 篇 accuracy
195 篇 feature extracti...
155 篇 computational mo...
146 篇 training
117 篇 deep learning
115 篇 computer science
114 篇 real-time system...
105 篇 data mining
103 篇 support vector m...
95 篇 servers
95 篇 machine learning
94 篇 predictive model...
85 篇 artificial intel...
85 篇 data models
84 篇 cloud computing
83 篇 internet of thin...
81 篇 protocols
79 篇 computer archite...
79 篇 semantics
78 篇 quality of servi...

机构

115 篇 dept. of compute...
85 篇 dept. of informa...
76 篇 institute of inf...
60 篇 dept. of informa...
56 篇 dept. of compute...
52 篇 dept. of compute...
44 篇 dept. of compute...
41 篇 dept. of compute...
37 篇 dept. of compute...
33 篇 dept. of compute...
28 篇 dept. of compute...
26 篇 dept. of compute...
22 篇 school of automa...
22 篇 dept. of compute...
21 篇 graduate institu...
20 篇 dept. of compute...
20 篇 dept. of compute...
19 篇 dept. of informa...
17 篇 dept. of compute...
17 篇 dept. of informa...

作者

46 篇 lorenzo bruzzone
25 篇 li kuan-ching
22 篇 jian-jhih kuo
20 篇 libertario demi
20 篇 yen-lin chen
19 篇 ren-hung hwang
18 篇 mei-hui wang
18 篇 chen yen-lin
18 篇 luca turchet
16 篇 francesca bovolo
16 篇 chang-shing lee
16 篇 hwang ren-hung
15 篇 kwon soonhak
15 篇 jia-ching wang
15 篇 hung yi-ping
14 篇 lee yue-shi
14 篇 bae hae-young
13 篇 horng shi-jinn
13 篇 watabe hirokazu
13 篇 wu eric hsiao-ku...

语言

6,210 篇 英文
783 篇 其他
57 篇 中文
19 篇 日文
6 篇 朝鲜文
3 篇 斯洛文尼亚文

检索条件"机构=Dept. of Computer Science& Information Engineering"

共 7075 条记录，以下是871-880 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

All patched up: Effective integration of real and synthetic features into a single image for object detection

All patched up: Effective integration of real and synthetic ...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Dale, Ashley S. Christopher, Lauren Reindl, William Sanchez, Edwin Brunes, Sam Bickel, Will Martin, Jasmine William, Albert Indiana University Purdue University Indianapolis Dept. of Electrical and Computer Engineering IndianapolisIN46202 United States Indiana University Purdue University Indianapolis Dept. of Computer and Information Science IndianapolisIN46202 United States Indiana University Purdue University Indianapolis Dept. of Human-Centered Computing Media Arts and Sciences Indiana IndianapolisIN46202 United States

ISBN: (纸本)9798350359527

Synthetic data and data augmentation are commonly used to supplement a small set of real images and create a dataset with diverse features, improving the robustness of a computer vision model. However, there is no consensus on how to best leverage synthetic data for object detection tasks in a real environment. Our work answers the following questions: First, is it more important for synthetic data to have realistic backgrounds or realistic instances? Second, is pixel saliency a valid metric for explaining the relative importance of real and synthetic instances? We explore these questions by placing synthetic object instances in real environments and vice versa to create synthetically blended data, rather than a dataset with distinct real and synthetic images. Our results show that when there is good overlap between the feature domains of the real and synthetic images, there is no benefit to augmenting the training data with patches. However, given a domain gap between real and synthetic data for a given class, model performance improved ≈ 60%, with greater gains observed when increasing the number of images with real backgrounds. These results show that the relationship of synthetic to real features should be considered when constructing a dataset for domain transfer tasks. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Lightweight Neural Networks for Adversarial Defense: A Novel NTK-Guided Pruning Approach

Lightweight Neural Networks for Adversarial Defense: A Novel...

引用

Open Innovations Association (FRUCT), Conference of

作者： Akhila Reddy Yadulla Bhargavi Konda Mounica Yenugula Vinay Kumar Kasula Sarath Babu Rakki Rajkumar Banoth Dept. of Information Technology University of the Cumberlands Williamsburg KY USA Dept. of Computer Science and Engineering JNTUH College of Engineeting Hyderabad TG India Dept. of Computer Science University of Texas at San Antonio San Antonio TX USA

ISBN: (数字)9789526524634

ISBN: (纸本)9798331595425

Self-Supervised Adversarial Training (SSAT) is a widely used adversarial attack defense method that integrates adversarial examples into the training process, effectively enhancing robustness against attacks. However, the robustness of SSAT models often relies on increasing network capacity, leading to a significant enlargement of model size and restricting its usability. A major challenge is to develop a lightweight adversarial defense method that maintains robustness while reducing model capacity. To address this issue, we propose a novel lightweight adversarial attack defense approach based on Neural Tangent Kernel (NTK)-Guided Pruning and Attention-Based Robust Distillation, integrated with Friendly Adversarial Training (FAT). Our method optimizes adversarial robustness by performing layer-wise adaptive NTK-guided pruning on a pre-trained adversarially robust model, followed by data-filtering-based Attention-Based Robust Distillation on the pruned network to retain essential robustness properties. Experimental evaluations on CIFAR-10 and CIFAR-100 datasets demonstrate that under the same FAT adversarial training setting, our proposed NTK-guided pruning method outperforms existing pruning techniques, yielding a more robust network structure across different FLOPs settings. Furthermore, the combination of NTK-guided pruning and Attention-Based Robust Distillation achieves higher adversarial robustness accuracy compared to other robust distillation techniques. These results validate that our approach successfully reduces adversarial training model capacity while improving robustness, making it highly suitable for edge computing environments in the Internet of Things (IoT).

关键词： Training Adaptation models Technological innovation Accuracy Neural networks Robustness Fats Neural architecture search Internet of Things Usability

来源：评论

学校读者我要写书评

暂无评论

Experiences Teaching Data Structures at HBCUs (and the Case for Cultural Pedagogy)

Experiences Teaching Data Structures at HBCUs (and the Case ...

引用

Research in Equity and Sustained Participation in engineering, Computing, and Technology (RESPECT)

作者： Simone A. Smarr Juan E. Gilbert Dept. of Computer & Information Science & Engineering University of Florida Gainesville FL USA

ISBN: (数字)9798350328325

ISBN: (纸本)9798350328332

As computing education research seeks to be more equitable, it is important to identify the needs of minority groups, like those at Historically Black Colleges and Universities (HBCUs) specifically, and understand how these groups are being engaged in learning. Basic data structures are a foundational topic for computing students’ academic advancement and career success. To understand the trends in how data structure topics are being taught at HBCUs through the lens of professors, we conducted semi-structured interviews. These experiences showed that there is promise for a more direct/intentional application of culturally sustaining pedagogy to data structures instruction.

关键词： computer science engineering profession Education engineering computing Data structures Market research Cultural differences

来源：评论

学校读者我要写书评

暂无评论

An Efficient Visual Cryptography Approach for Intermodal Biometric Verification

An Efficient Visual Cryptography Approach for Intermodal Bio...

引用

2022 International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2022

作者： Das, Abhishek Ganguly, Nabanita Mit Art Design & Technology University Dept. of Computer Science & Engineering Pune India Maulana Abul Kalam Azad University of Technology Dept. of Information Technology Haringhata India

ISBN: (纸本)9781665454995

Biometric authentication is one of the important ways of acknowledging an individual using their behavioral and physical characteristics. It can range from fingerprint to an iris or retina image, hand geometry, gait or signature, or some other physiological characteristics. The biometric authentication can be further sub-classified into unimodal and multimodal biometric authentication. The framework of biometrics, which utilizes only one suggestive option for verification is termed unimodal biometric. On the other hand, a lot of research work has been going on for the last two decades on multimodal biometric systems where more than one biometric detail of an individual is collected and used in order to authenticate a person. In other words, it can be said that in a multimodal biometrics system, more than two or sometimes at least two biometric sources of one individual (i.e., iris, dermatoglyphics) are considered and evaluated. In our paper, we have implemented an efficient way of fusing two biometric images (human fused iris image of both two eyes and fused thumb impression of two hands) into one image and converted the color image into a binary image, and used the (2,2) Visual Cryptography Scheme two efficiently create two out of two shares. As part of the reconstruction, we have overlapped the two generated shares to generate the fused image. The fused image was further processed to authenticate the genuine person. The proposed approach reduces storage costs and uses simple steps to implement the project which is easy to understand by non-technical people as well. © 2022 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

FloraNet: An Approach to Prediction of Sea Buckthorn Disease based on a Convolutional Neural Network and a Random Forest Method

FloraNet: An Approach to Prediction of Sea Buckthorn Disease...

引用

Emerging Technology (INCET), International Conference for

作者： J. Pushpakumari Nuthanakanti Bhaskar G. Divya Murali Kanthi K. Srujan Raju Jonnadula Narasimharao Dept. of Computer Science and Engineering (AIML & IOT) VNRVJIET Hyderabad Telangana India Dept. of Computer Science and Engineering CMR Technical Campus Hyderabad Telangana India Dept. of Information Technology CMR Technical Campus Hyderabad Telangana India Department of Computer Science & Engineering (Data Science) CMR Technical Campus Hyderabad Telangana India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

In the current study, FloraNet was used to present an improved method for diagnosing leaf diseases in Sea Buckthorn. In the proposed model, Convolutional Neural Networks (CNN) and Random Forests (RF) are integrated. Essentially, CNN architecture is composed of a pair of convolutional layers, followed by a max-pooling layer; it is then followed by another pair of convolutional layers, before finishing off with a final pair of convolutional layers. Performance indicators such as Precision, Recall, F1-Score, or Accuracy are used to determine the performance of the model in terms of its performance. There were five disorders under investigation: Phakopsora, Erysiphe, Septoria, Colletotrichum, Phoma, as well as viral infections. Overall, the results show that the Micro Average accuracy for all classes is 95.11 %. According to the results, the individual accuracy ranges from 0.98 to 0.99 for each illness, while the F1-Scores range from 94.02% to 95.91% for each illness. This study concludes that the weighted average accuracy of 95.11 demonstrates a high level of proficiency of the model in identifying diseases, and indicates that the model is capable of identifying a wide variety of diseases. By using this integrated approach, agricultural scientists and researchers are able to detect Sea Buckthorn leaf diseases.

关键词： Measurement Accuracy Sea measurements Forestry Predictive models Solids Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Data Hiding in Neural Compressed Latent Representations

Image Data Hiding in Neural Compressed Latent Representation...

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Chen-Hsiu Huang Ja-Ling Wu Dept. of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message encoder and decoder, our approach simultaneously achieves high image quality and high bit accuracy. Compared to existing techniques, our framework offers superior image secrecy and competitive watermarking robustness in the compressed domain while accelerating the embedding speed by over 50 times. These results demonstrate the potential of combining data hiding techniques and neural compression and offer new insights into developing neural compression techniques and their applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explainability to Business: Demystify Transformer Models with Attention-based Explanations

Explainability to Business: Demystify Transformer Models wit...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Rajasekhar Thiruthuvaraj Ashly Ann Jo Ebin Deni Raj Dept. of Computer Science & Engineering Indian Institute of Information Technology Kottayam India

Recently, many companies are relying on Natural Language Processing (NLP) techniques to understand the text data generated daily. It has become very critical to deal with this data because finding the sentiments of text and summarizing them will help the company understand the pain points of the customers posting reviews on social media or understand the experience of the customer. These requirements have increasingly demanded many advanced algorithms to deal the text data. The introduction of Transformers led to businesses adopting NLP methods more and more to keep up with their needs. Models like Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT), state-of-the-art results were achieved with billions of parameters learned. Although these advancements improved the accuracy and expanded the use of algorithms to a wide range of NLP tasks like language translation, text summarization, and language modeling. Businesses are more interested in the Explainability of the model compared to its accuracy. Explainable Artificial Intelligence (XAI) plays an important role to comprehend the complexities of the model as well as the influence of weights on predictions. In this paper, the complexities of the transformer model are unraveled by presenting a straightforward method for computing explainable predictions. The DistilBERT model is chosen as an example to implement the explainable system due to its lighter nature. Combining the strengths of a Posthoc expla-nation with those of a self-learning neural network, the method makes it simple to scale it to other algorithms to implement. With technologies like python, PyTorch, and Hugging Face, a detailed step-by-step algorithmic computation is demonstrated to explain the predictions from the attention-based explanations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using a Design Pattern to Build Microservices for Instant Messaging Software to Access IoT Devices

Using a Design Pattern to Build Microservices for Instant Me...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Hsin-Yu Huang Yong-Yi Fanjiang Hsing-Yu Tsai Yung-Shiang Huang Yi-Shiang Yu Dept. of Digital Multimedia Lee-Ming Institute of Technology New Taipei City Taiwan Dept. of Computer Science and Information Engineering Graduate Institute of Applied Science and Engineering Fu Jen Catholic University New Taipei City Taiwan Dept. of Computer Science and Information Engineering Fu Jen Catholic University New Taipei City Taiwan

ISBN: (数字)9798350355079

ISBN: (纸本)9798350355086

This study introduces a design pattern to build microservices, which provides an opportunity for instant messaging software developers, Internet of Things(IoT) device manufacturers and third parties to deploy themselves belonging to the APIs in microservices. Users can use instant messaging software to access IoT devices through the APIs deployed by the system. Instant messaging software developers, IoT device manufacturers and third parties can develop and deploy APIs in Instant Messaging (IM) microservice and IoT microservice of this system based on the OpenAPI specification document using a design pattern. The goal of this system is for users to use the installed and usually used instant messaging software without having to install and learn new app to access various IoT devices.

关键词： Microservice architectures Instant messaging Software Internet of Things Smart phones Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-label text classification using adaptive promptify concepts

Enhancing Multi-label text classification using adaptive pro...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Veerababu Reddy Usha Rani Uppukonda N. Veeranjaneyulu Dept. of Computer Science & Engineering Vignan’s Foundation for Science Technology & Research Guntur India Dept. of Computer Science & Engineering Vignan’s Lara Institute of Technology & Science College Guntur India Dept. of Information Technology Vignan’s Foundation for Science Technology & Research Guntur India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In present days, Multi Label Text Classification (MLTC) has become an important research area in Natural Language Processing (NLP). Existing models of MLTC have been facing domain specificity and fine-tuning challenges. Hence a model is developed to overcome the above said challenges by introducing Prompt engineering, GPT FineTuning methods and Pipeline algorithms. The experimental results are obtained based on the present Generative pre trained data produces labels for various text documents and files with an exceptional accuracy of 85%. The outcomes of the experiments reveal notable enhancements over the baseline models.

关键词： Surveys Accuracy Social networking (online) Text categorization Pipelines Medical services Natural language processing Prompt engineering Optimization Sorting

来源：评论

学校读者我要写书评

暂无评论

Classwise Self-Paced Self-Training for Semi-Supervised Image Classification

Classwise Self-Paced Self-Training for Semi-Supervised Image...

引用

Asia-Pacific Signal and information Processing Association Annual Summit and Conference (APSIPA)

作者： Cheng-Yu Lu Heng-Cheng Hsu Chen-Kuo Chiang Dept. of Computer Science and Information Engineering National Chung Cheng University Taiwan

In recent years, self-training has become more and more popular in model learning because it only requires a small amount of labeled data to reach high classification accuracy. Since the conventional self-training does not perform in a class-specific manner, class imbalance problem happens frequently as self-training tends to select more pseudo labeled samples from easy classes. It becomes even worse when training dataset is originally class-imbalanced. In this paper, classwise self-paced self-training is proposed to solve this problem. A classwise pseudo-labeling method ensures that sufficient data are selected for each class in a self-pace manner. To avoid increasing number of noisy samples, two indicators, confidence score and uncertainty score, are proposed based on dropout prediction for noisy label filtering. Experimental results demonstrate that the proposed method achieves very competitive performance on CIFAR-10 and ISIC2018 datasets. Keyword: Deep Learning, Image Classification, Semi-Supervised Learning, Self-Training

关键词：

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 84 85 86 87 88 89 90 91 92 93 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：